Hugging Face's logo

ClarenceDan
/
c10aae00-6554-4622-9e0e-9c3b568b0731

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
1
c10aae00-6554-4622-9e0e-9c3b568b0731
File size: 3,207 Bytes 
cabc5fc
 
 
b51bbf9
cabc5fc
b51bbf9
cabc5fc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d66f6a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c494011
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b51bbf9
 
 
 
 
 
 
cabc5fc
 
 
 
 
 
 
 
 
 
 
 
 
 
b51bbf9
cabc5fc
 
 
 
b51bbf9
cabc5fc
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0014825796886582653,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014825796886582654,
      "grad_norm": 0.7877658605575562,
      "learning_rate": 2e-05,
      "loss": 1.4327,
      "step": 1
    },
    {
      "epoch": 0.00014825796886582654,
      "eval_loss": 1.423957109451294,
      "eval_runtime": 53.3401,
      "eval_samples_per_second": 53.243,
      "eval_steps_per_second": 26.622,
      "step": 1
    },
    {
      "epoch": 0.0002965159377316531,
      "grad_norm": 0.63080233335495,
      "learning_rate": 4e-05,
      "loss": 1.3985,
      "step": 2
    },
    {
      "epoch": 0.00044477390659747963,
      "grad_norm": 0.7581550478935242,
      "learning_rate": 6e-05,
      "loss": 1.4602,
      "step": 3
    },
    {
      "epoch": 0.00044477390659747963,
      "eval_loss": 1.4189095497131348,
      "eval_runtime": 53.5812,
      "eval_samples_per_second": 53.004,
      "eval_steps_per_second": 26.502,
      "step": 3
    },
    {
      "epoch": 0.0005930318754633062,
      "grad_norm": 0.6960687637329102,
      "learning_rate": 8e-05,
      "loss": 1.3669,
      "step": 4
    },
    {
      "epoch": 0.0007412898443291327,
      "grad_norm": 0.699456512928009,
      "learning_rate": 0.0001,
      "loss": 1.5292,
      "step": 5
    },
    {
      "epoch": 0.0008895478131949593,
      "grad_norm": 0.778120756149292,
      "learning_rate": 0.00012,
      "loss": 1.3721,
      "step": 6
    },
    {
      "epoch": 0.0008895478131949593,
      "eval_loss": 1.3613526821136475,
      "eval_runtime": 53.5086,
      "eval_samples_per_second": 53.076,
      "eval_steps_per_second": 26.538,
      "step": 6
    },
    {
      "epoch": 0.0010378057820607859,
      "grad_norm": 0.6381222009658813,
      "learning_rate": 0.00014,
      "loss": 1.3513,
      "step": 7
    },
    {
      "epoch": 0.0011860637509266123,
      "grad_norm": 0.6122051477432251,
      "learning_rate": 0.00016,
      "loss": 1.4294,
      "step": 8
    },
    {
      "epoch": 0.0013343217197924388,
      "grad_norm": 0.6916836500167847,
      "learning_rate": 0.00018,
      "loss": 1.2368,
      "step": 9
    },
    {
      "epoch": 0.0013343217197924388,
      "eval_loss": 1.305905818939209,
      "eval_runtime": 54.3713,
      "eval_samples_per_second": 52.233,
      "eval_steps_per_second": 26.117,
      "step": 9
    },
    {
      "epoch": 0.0014825796886582653,
      "grad_norm": 0.8482385277748108,
      "learning_rate": 0.0002,
      "loss": 1.421,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 155816786657280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}